Network User Activity Analysis via Propagation Graphs and Action History
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current techniques fail to effectively characterize user activities and purposes on a network, limiting efficient information distribution and user profiling.
Innovation Solution
An analysis system comprising an attribute extraction block, an information propagation graph acquisition block, and a characteristic user calculation block to extract information characteristics, search action history data, and calculate user characteristics, integrating them to characterize user activities and purposes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If only information propagation routes are traced using directed graphs, then information flow between users can be tracked, but the purpose and role of users in information propagation cannot be determined
Solution Approach 1:
The patent segments the analysis into multiple components: information propagation graph for tracking flow, action history data for user behaviors, and attribute extraction for content characteristics. Each segment addresses a specific aspect of user analysis, collectively enabling comprehensive purpose detection that单一的 directed graph cannot achieve
Solution Approach 2:
The patent adds new dimensions to the analysis by incorporating action history data (user behaviors over time) and attribute extraction (content characteristics) alongside the traditional information propagation graph. This multi-dimensional approach transforms 2D propagation tracking into a multi-faceted analysis that reveals user purposes and roles
2Productivity
If user activities on the network are analyzed based on information propagation, then propagation routes can be detected, but the difference in user purposes and preferences cannot be reflected
Solution Approach 1:
The patent introduces action history data and attribute extraction as intermediary elements that mediate between information propagation tracking and user purpose characterization. These intermediaries bridge the gap by providing additional context (user actions and content attributes) that enable precise purpose detection while maintaining propagation analysis efficiency
Solution Approach 2:
The patent changes the parameters of analysis by incorporating multiple data types (propagation graphs, action histories, content attributes) with different characteristics. This parameter diversification enables the system to capture both the efficiency of information propagation and the nuances of user purposes and preferences
3Measurement precision
If comprehensive user activity data is collected to characterize user purposes, then accurate user profiling can be achieved, but system complexity increases
Solution Approach 1:
The patent divides the complex analysis system into modular segments: information propagation graph acquisition, action history data processing, attribute extraction, and characteristic user calculation. Each module handles a specific data type or processing task, making the overall complex system manageable and maintainable while achieving accurate user purpose detection
Solution Approach 2:
The patent creates a multi-functional analysis system where each component serves multiple purposes: the information propagation graph tracks information flow and provides structural context, action history data captures user behaviors and temporal patterns, and attribute extraction identifies content characteristics. This universality allows comprehensive user characterization without requiring separate specialized systems for each data type
Data Source
AI summary
An analysis system, information processing apparatus, activity analysis method, and program for analyzing activities of an information source on a network. The system and apparatus include an attribute extraction block for extracting, an information propagation graph acquisition block for searching action history data, and a characteristic user calculation block for calculating an amount characteristic. The method and program product include the steps of extracting an information characteristic value, searching action history data, registering the information, calculating an amount characteristic, and integrating the amount characteristic.